Production readiness

A production Northsun integration is ready when authentication is server-side, the recall/write-back lifecycle is observable, failure modes preserve the agent experience, and every public claim matches behavior you have actually observed.

Before launch

• [ ] Store NORTHSUN_API_KEY (or whatever variable your deployment names it) in a managed secret store and confirm it never reaches browser or mobile code.
• [ ] Pin the npm package version you tested; do not assume the repository version is the published version.
• [ ] Use E.164 phone numbers and URL-encode path parameters.
• [ ] Set an end-to-end request deadline before the first network call.
• [ ] Treat missing enrichment as a partial response, not a failed conversation.
• [ ] Select context deliberately: recall_and_enrich returns stored caller memory newest call first, up to five, not ranked by relevance to the current call. Your application decides what reaches the prompt.
• [ ] Handle 400, 401, 404, 422, 429, timeouts, and temporary 5xx responses separately.
• [ ] Add capped backoff with jitter only for retryable failures.
• [ ] Deduplicate voice-platform webhook retries by the platform call identifier.
• [ ] Confirm calls/end is called once after hangup, treat 204 as confirmation that the interaction is committed durably, and verify that it is visible with a later controlled recall.
• [ ] Record endpoint, status, trace ID, and safe correlation metadata without logging secrets or PII.

Prove the lifecycle

Use a controlled test number on a tenant issued to you through the contact form:

1. Call recall_and_enrich and retain its trace ID.
2. Call calls/end with a short synthetic transcript and the same session_id.
3. Confirm the 204 response: the interaction is committed durably.
4. Call recall_and_enrich again and verify the expected history is present. It normally appears but may lag, so repeat the recall after a short, bounded interval before treating its absence as a failure.
5. Call GET /v1/caller/{phone_number} and verify the read-only profile.
6. Exercise one validation failure and one rate-limit/retry path in your own non-production environment; Northsun has no sandbox.

This proves your mapping and lifecycle. It does not prove a universal latency benchmark, customer outcome, compliance posture, or every dependency state.

Voice fail-open behavior

Design the surrounding agent so unavailable optional context does not prevent a call from continuing. A safe fallback greeting should not reveal whether enrichment failed, and it should never guess a person's identity.

Change management

• Follow the changelog for contract and client changes.
• Pin package versions and update deliberately.
• Re-run the lifecycle proof after changing voice-platform webhooks, key configuration, phone normalization, or client versions.
• Keep a kill switch for any autonomous workflow that sends, posts, spends, or performs an irreversible action.

Next steps

• Troubleshooting — diagnostic matrix.
• Errors and retries — retry policy.
• TypeScript client or Python over HTTP — implementation guides.